Hello! This week’s research recap features the most relevant investing insights from the past seven days, drawing on academic papers, blogs, and industry reports, with direct links to every source.
Crypto
Cryptocurrency as an Investable Asset Class: Coming of Age (Borri, Liu, Tsyvinski, and Wu)
This paper describes 10 stylized facts about cryptocurrencies, including their 5× higher volatility but similar Sharpe ratios to equities, a rising correlation with stocks (2% to 37% post-2020) yet strong diversification benefits, frequent large jumps that complicate risk management, and the declining profitability of the crypto-carry trade. A small set of factors, market, size, momentum, and value, explains most returns. Key takeaway: Crypto is maturing into a mainstream asset class, increasingly resembling equities while retaining some unique risks.
A crypto-stock weekend effect: Predicting Monday stock returns using weekend cryptocurrency returns (Mourey, Shahrour, and Soiman)
Negative weekend returns in major cryptocurrencies predict Monday declines in U.S. equities, whereas positive returns have no effect. Across 20 large-cap cryptocurrencies, 16 exhibit strong predictive spillovers. This asymmetric relationship strengthened after the May 2022 LUNA collapse, indicating a turning point in the transmission of crypto shocks to stocks.. Key takeaway: Weekend crypto selloffs may serve as early-warning signals of Monday stock market weakness.
Equities
Economic Linkages Inferred from News Stories and the Predictability of Stock Returns (Scherbina and Schlusche)
The authors identify related firms by tracking how companies are co-mentioned in news stories, uncovering lead–lag return predictability. For each firm, the past-month returns of its co-mentioned peers predict its next-month performance, suggesting slow information diffusion across economically connected companies. From 1996 to 2024, sorting by this signal yields about a 0.3% monthly six-factor alpha. Key takeaway: Media co-mentions uncover short-lived information linkages that create profitable cross-firm predictability, not captured by traditional methods of identifying related firms.
Enhancing global equity returns with trend-following and tail risk hedging overlays (Schwalbach and Auret)
Overlaying trend-following and 10-delta SPX put option hedges on a global equity portfolio meaningfully boosts performance without reducing equity exposure. A portable alpha portfolio built this way achieves a CAGR of 11.02% vs. 8.06%, a Sharpe ratio of 0.66 vs. 0.37, and a monthly alpha of 0.25%. Drawdowns are nearly halved (-19.1% vs. -34.3%) and negative skewness largely eliminated. Key takeaway: Combining convex overlays with equity beta improves returns and resilience, especially in crises.
Equity Valuation Without DCF (Cho, Polk, and Rogers)
This paper introduces discounted alpha, a valuation method that prices stocks as the current price plus the present value of expected future alphas relative to an asset pricing model like CAPM, rather than discounting distant cash flows. Across 2.6 million stock-months (1953–2024), it shows private equity buys 13% below and exits 17% above fair value, analyst optimism fuels mispricing, and profitable, low-beta, high-B/M stocks are most undervalued. Key takeaway: Discounted alpha offers more robust valuations and actionable signals than the traditional DCF model.
Extreme-weather risk and the cross-section of stock returns (Braun, Braun, Weigert)
U.S. stocks most vulnerable to storm-related losses earn over 6% higher annual excess returns than those that benefit from extreme weather, a risk premium unexplained by standard factors. A portfolio long these high-risk stocks and short the least exposed delivers roughly 0.54% per month and remains robust to seasonality and controls. The effect is concentrated in companies operating in storm-prone regions, with a history of weather damage, and with significant institutional ownership. Key takeaway: Extreme-weather exposure commands a risk premium in U.S. equities of roughly 6% annually.
Machine Learning and Large Language Models
Disagreement on Tail (Chen, Chen, Li, and Luo)
This paper introduces Disagreement on Tail (DOT), a measure of how much investors’ beliefs diverge about rare downside events. For each stock and month, 100 neural networks, each simulating an investor, forecast the probability of a –25% return, and DOT is the standard deviation of these forecasts. Stocks with high DOT are overpriced and underperform: A low-minus-high DOT portfolio earns 1.07% per month. Key takeaway: Extreme-event belief dispersion signals overvaluation where shorting high-DOT stocks and buying low-DOT ones generates alpha.
Your AI, Not Your View: The Bias of LLMs in Investment Analysis (Lee, Seo, Park, Lee, Ahn, Choi, Lopez-Lira, and Lee)
LLMs show clear investment biases, favoring technology and large-cap stocks while preferring contrarian over momentum strategies. Even when most evidence opposed their view, models rarely changed course, revealing strong confirmation bias. Key takeaway: Financial LLMs carry persistent preferences that may affect users’ decision-making; their recommendations should therefore be treated with caution in investment contexts.
Increase Alpha: Performance and Risk of an AI-Driven Trading Framework (Ghatak, Khaledian, Parvini, and Khaledian)
This paper develops a deep-learning trading framework using compact feed-forward and recurrent networks with economically grounded features. It predicts daily directions for 814 U.S. stocks and trades them via optimized profit-taking and stop-loss rules. From 2021 to 2025, the system delivers a gross Sharpe ratio of about 2.5, a max drawdown of about 3%, and a near-zero correlation to the S&P 500. Key takeaway: Expert-curated deep learning can produce robust and uncorrelated returns with superior Sharpe ratios.
Options
NDX 1-Day Straddle Pricing: Are there Better Days than Others to Buy or Sell Straddles? (Rhoads)
Between 2022 and Q3 2025, buying 1-day at-the-money NDX straddles earned a total profit of about 3,094 points, while consistently shorting them lost about 6,438 points, contradicting the usual advantage of option sellers. Monday expirations, priced before the weekend, were the only profitable short-vol trade (+1,821 points, 61% win rate), reflecting a weekend overpricing effect. In contrast, Wednesday to Friday straddles were underpriced and favored buyers. Key takeaway: 0DTE NDX options show weekday mispricing, favoring being short vol over the weekend, while mid-week favors long-vol positions.
Blogs
The End-Of-Month Effect in Value–Growth and Real‑Estate–Equity Spreads (Quantpedia)
Building a Smarter TAA Model for Stronger Returns and Lower Risk (Quantseeker)
Swiss reflections (John H. Cochrane)
Podcasts
The Hedge Fund Trader Who Automates Everything: Rob Carver (Two Blokes Trading)
Talk Your Book: Value + Momentum: The Best of Both Factors (Animal Spirits)
Sharpe Ratios, Tail Risks, and the Cost of Comfort ft. Nigol Koulajian & Alan Dunne (Top Traders Unplugged)
Social Media / Industry Research
A little peep inside one of London’s hot new quant powerhouses (FT Alphaville)
The Challenge of Diversification (Dan Rasmussen, Verdad)
Understanding Gold (Campbell Harvey)
A Trend Following Deep Dive: AI, Agents and Trend (Man Group)
Last Week’s Most Popular Links
The New Quant: A Survey of Large Language Models in Financial Prediction and Trading (Fu)
Volatility forecasting for low-volatility investing (Conrad, Kleen, and Lönn)
Peer Option Momentum (Jones, Khorram, Li, Mo, Yang, and Zhang)
Disclaimer: This newsletter is for informational and educational purposes only and should not be construed as investment advice. The author does not endorse or recommend any specific securities or investments. While information is gathered from sources believed to be reliable, there is no guarantee of its accuracy, completeness, or correctness.
This content does not constitute personalized financial, legal, or investment advice and may not be suitable for your individual circumstances. Investing carries risks, and past performance does not guarantee future results. The author and affiliates may hold positions in securities discussed, and these holdings may change at any time without prior notification.
The author is not affiliated with, sponsored by, or endorsed by any of the companies, organizations, or entities mentioned in this newsletter. Any references to specific companies or entities are for informational purposes only.
The brief summaries and descriptions of research papers and articles provided in this newsletter should not be considered definitive or comprehensive representations of the original works. Readers are encouraged to refer to the original sources for complete and authoritative information.
This newsletter may contain links to external websites and resources. The inclusion of these links does not imply endorsement of the content, products, services, or views expressed on these third-party sites. The author is not responsible for the accuracy, legality, or content of external sites or for that of any subsequent links. Users access these links at their own risk.
The author assumes no liability for losses or damages arising from the use of this content. By accessing, reading, or using this newsletter, you acknowledge and agree to the terms outlined in this disclaimer.